Bin Zhang

This paper identifies RNA G-quadruplexes as temperature and potassium sensors that regulate alternative splicing and neuroprotection in subarachnoid hemorrhage.

AutoBA is an AI agent that automates multi-omic analyses using large language models, offering adaptability and security across various sequencing and omics data types.

PPML-Omics is a privacy-preserving federated learning method that balances privacy protection and model utility across three omic data tasks.

GenSLMs use large language models to analyze SARS-CoV-2 genomes, enabling rapid identification of variants of concern and providing insights into evolutionary dynamics.

The paper introduces AFS, a tool to revoke patients' private data from pre-trained models by auditing usage and purifying knowledge, tested across multiple tasks and datasets.

DeepTRs identifies tandem repeat variations directly from Nanopore reads using multi-modal conversion and deep learning, achieving high sensitivity, accuracy, and completeness.

DeeReCT-TSS improves TSS annotation across cell types using DNA sequences and RNA-seq data, outperforming sequence-only methods and enabling cell-type-specific TSS identification.

DeeReCT-APA quantitatively predicts alternative polyadenylation site usage across genes using a deep learning model, outperforming existing methods in multiple tasks.

The paper analyzes RBP expression across 16 cancer types, identifies upregulated and downregulated RBPs, and links their expression to copy number and DNA methylation, suggesting roles in tumorigenesis.

The paper identifies a multiscale temporal regulatory network involving genes that regulate circadian, cell cycle, and aging processes, enriched for signal transduction, metabolism, and stress response genes.

Mergeomics integrates diverse genomics resources to identify pathogenic perturbations by analyzing disease-associated pathways and gene networks, revealing novel cholesterol regulators.